Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 875 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.3324. Min Act: -0.1700

Data Index: 5927826 (Open Web Text)

Max Activating Token Index: 134

Text #1

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.3145. Min Act: -0.1700

Data Index: 5927814 (Open Web Text)

Max Activating Token Index: 44

Text #2

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.2490. Min Act: -0.1700

Data Index: 6853525 (Open Web Text)

Max Activating Token Index: 296

Text #3

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1944. Min Act: -0.1700

Data Index: 6853526 (Open Web Text)

Max Activating Token Index: 92

Text #4

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1898. Min Act: -0.1700

Data Index: 6853528 (Open Web Text)

Max Activating Token Index: 167

Text #5

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1952. Min Act: -0.1700

Data Index: 5927823 (Open Web Text)

Max Activating Token Index: 60

Text #6

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1899. Min Act: -0.1700

Data Index: 5927825 (Open Web Text)

Max Activating Token Index: 214

Text #7

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.2035. Min Act: -0.1700

Data Index: 5554168 (Open Web Text)

Max Activating Token Index: 285

Text #8

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1938. Min Act: -0.1700

Data Index: 5927828 (Open Web Text)

Max Activating Token Index: 249

Text #9

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1896. Min Act: -0.1700

Data Index: 5927830 (Open Web Text)

Max Activating Token Index: 118

Text #10

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1495. Min Act: -0.1700

Data Index: 5927813 (Open Web Text)

Max Activating Token Index: 229

Text #11

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1548. Min Act: -0.1700

Data Index: 3425979 (Open Web Text)

Max Activating Token Index: 309

Text #12

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1502. Min Act: -0.1700

Data Index: 2525151 (Open Web Text)

Max Activating Token Index: 135

Text #13

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1517. Min Act: -0.1700

Data Index: 5927816 (Open Web Text)

Max Activating Token Index: 463

Text #14

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1492. Min Act: -0.1700

Data Index: 7164579 (Open Web Text)

Max Activating Token Index: 240

Text #15

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1653. Min Act: -0.1700

Data Index: 2525141 (Open Web Text)

Max Activating Token Index: 109

Text #16

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1311. Min Act: -0.1700

Data Index: 3425978 (Open Web Text)

Max Activating Token Index: 513

Text #17

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1346. Min Act: -0.1700

Data Index: 6853517 (Open Web Text)

Max Activating Token Index: 157

Text #18

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1116. Min Act: -0.1700

Data Index: 5927819 (Open Web Text)

Max Activating Token Index: 46

Text #19

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.1234. Min Act: -0.1700

Data Index: 2525149 (Open Web Text)

Max Activating Token Index: 128